{"uid":"cap_SboR71MjDT83oftWAHJiI","slug":"feature-availability-analytics-record-quality-audit-string-1a5f7390","name":"Feature Availability Analytics — Record Quality Audit, String Normalisation & Secondary-Measure Weighted Mean","description":"Feature availability — Record quality audit + String normalisation + Secondary-measure weighted mean: Record quality audit + String normalisation + Secondary-measure weighted mean for supplied feature availability records (populated_features, expected_features). Up to 200 rows; 3 independent reports using shared local analytical engines. No live lookup, prediction, professional assessment or external action. 0.01 USDC includes 3 supplied-data reports for up to 200 rows.","url":"https://market.datapackvibe.com/x402/assistant-ib26-analytics-10-205?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"rows":{"type":"array","items":{"type":"object","required":["row_id","dataset_group","date","populated_features","expected_features"],"properties":{"date":{"type":"string","default":"","pattern":"^\\d{4}-\\d{2}-\\d{2}$","maxLength":10},"row_id":{"type":"string","default":"","maxLength":80,"minLength":1},"dataset_group":{"type":"string","default":"","maxLength":80},"expected_features":{"type":["number","null"],"maximum":1000000000000,"minimum":-1000000000000},"populated_features":{"type":["number","null"],"maximum":1000000000000,"minimum":-1000000000000}},"additionalProperties":false},"default":[{"date":"2026-10-01","row_id":"row-1","dataset_group":"group-a","expected_features":1,"populated_features":10},{"date":"2026-10-02","row_id":"row-2","dataset_group":"group-b","expected_features":2,"populated_features":20},{"date":"2026-10-03","row_id":"row-3","dataset_group":"group-a","expected_features":3,"populated_features":15},{"date":"2026-10-04","row_id":"row-4","dataset_group":"group-b","expected_features":4,"populated_features":30}],"maxItems":200,"minItems":1},"field":{"enum":["populated_features","expected_features"],"type":"string","default":"populated_features"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_NBjts5R1E0qzYD77Hjqr5","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Runs three bundled analytical reports (record quality audit, string normalisation, and secondary-measure weighted mean) on up to 200 feature availability records containing populated_features and expected_features fields.","exampleAgentPrompt":"Can you run a quality audit, string normalisation, and weighted mean analysis on my feature availability records? I have 4 rows: row-1 on 2026-10-01 in group-a with 10 populated and 1 expected, row-2 on 2026-10-02 in group-b with 20 populated and 2 expected, row-3 on 2026-10-03 in group-a with 15 populated and 3 expected, and row-4 on 2026-10-04 in group-b with 30 populated and 4 expected — use populated_features as the primary field.","exampleUseCases":[{"title":"ML pipeline feature completeness audit","prompt":"I need to audit my feature availability data before training — can you run a record quality audit, string normalisation, and weighted mean on these 10 rows from dataset groups 'train' and 'val', each with a date, populated_features, and expected_features count? Use populated_features as the field."},{"title":"Data engineering dataset group comparison","prompt":"Can you analyse these 50 feature availability records across groups 'raw', 'cleaned', and 'enriched' for quality issues, normalise any string fields, and give me a weighted mean of the expected_features column so I can compare completeness across groups?"},{"title":"Daily feature population monitoring report","prompt":"Run the three-part analytics bundle on my daily feature availability snapshot — 20 rows dated between 2026-11-01 and 2026-11-20, split across dataset groups 'prod' and 'staging', each row has populated_features and expected_features counts. I want the quality audit, string normalisation, and weighted mean for populated_features."}],"resultDescription":"Returns three independent analytical reports for the submitted feature availability rows: (1) a record quality audit identifying issues such as nulls, out-of-range values, and structural anomalies; (2) string normalisation results for relevant text fields; and (3) a secondary-measure weighted mean computed over the selected numeric field (populated_features or expected_features), all processed locally without external lookups.","failureModes":["Rows array empty or missing — validation error returned","More than 200 rows submitted — rejected with max-items error","Invalid date format (not YYYY-MM-DD) — schema validation failure","populated_features or expected_features out of allowed numeric range — rejected","field enum value not 'populated_features' or 'expected_features' — schema validation error","row_id missing or empty string — required field validation failure"],"whenToPreferThis":"Choose this endpoint when you need three co-located data quality operations (audit, normalisation, weighted mean) on feature availability records in a single low-cost call, avoiding the overhead of three separate API calls. Ideal for data engineering and MLOps workflows where feature completeness tracking is batched up to 200 rows and external lookups or predictions are not needed.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-19T12:46:55.598Z","isFirstParty":false,"canonicalSlug":"feature-availability-analytics-record-quality-audit-string-1a5f7390"}